netfilter: nf_tables: build-in filter chain type

index 1f7148fe0504..77c3c04c27ac 100644
@@ -1345,4 +1345,7 @@ struct nft_trans_flowtable {
 #define nft_trans_flowtable(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flowtable)
 
+int __init nft_chain_filter_init(void);
+void __exit nft_chain_filter_fini(void);
+
 #endif /* _NET_NF_TABLES_H */

81 lines not on this page · raw message

60 lines not on this page · raw message

69 lines not on this page · raw message

67 lines not on this page · raw message

index 9e4b1614ee39..97ec1c388bfe 100644
@@ -6584,6 +6584,8 @@ static int __init nf_tables_module_init(void)
 {
 	int err;
 
+	nft_chain_filter_init();
+
 	info = kmalloc(sizeof(struct nft_expr_info) * NFT_RULE_MAXEXPRS,
 		       GFP_KERNEL);
 	if (info == NULL) {

@@ -6618,6 +6620,7 @@ static void __exit nf_tables_module_exit(void)
 	rcu_barrier();
 	nf_tables_core_module_exit();
 	kfree(info);
+	nft_chain_filter_fini();
 }
 
 module_init(nf_tables_module_init);

77 lines not on this page · raw message

140 lines not on this page · raw message

398 lines not on this page · raw message

index 77c3c04c27ac..e26b94a61a99 100644
@@ -884,6 +884,8 @@ enum nft_chain_types {
  * 	@owner: module owner
  * 	@hook_mask: mask of valid hooks
  * 	@hooks: array of hook functions
+ *	@init: chain initialization function
+ *	@free: chain release function
  */
 struct nft_chain_type {
 	const char			*name;

@@ -892,6 +894,8 @@ struct nft_chain_type {
 	struct module			*owner;
 	unsigned int			hook_mask;
 	nf_hookfn			*hooks[NF_MAX_HOOKS];
+	int				(*init)(struct nft_ctx *ctx);
+	void				(*free)(struct nft_ctx *ctx);
 };
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,

index 9864f5b3279c..b5464a3f253b 100644
@@ -67,6 +67,16 @@ static unsigned int nft_nat_ipv4_local_fn(void *priv,
 	return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
+static int nft_nat_ipv4_init(struct nft_ctx *ctx)
+{
+	return nf_ct_netns_get(ctx->net, ctx->family);
+}
+
+static void nft_nat_ipv4_free(struct nft_ctx *ctx)
+{
+	nf_ct_netns_put(ctx->net, ctx->family);
+}
+
 static const struct nft_chain_type nft_chain_nat_ipv4 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,

@@ -82,6 +92,8 @@ static const struct nft_chain_type nft_chain_nat_ipv4 = {
 		[NF_INET_LOCAL_OUT]	= nft_nat_ipv4_local_fn,
 		[NF_INET_LOCAL_IN]	= nft_nat_ipv4_fn,
 	},
+	.init		= nft_nat_ipv4_init,
+	.free		= nft_nat_ipv4_free,
 };
 
 static int __init nft_chain_nat_init(void)

index c95d9a97d425..3557b114446c 100644
@@ -65,6 +65,16 @@ static unsigned int nft_nat_ipv6_local_fn(void *priv,
 	return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain);
 }
 
+static int nft_nat_ipv6_init(struct nft_ctx *ctx)
+{
+	return nf_ct_netns_get(ctx->net, ctx->family);
+}
+
+static void nft_nat_ipv6_free(struct nft_ctx *ctx)
+{
+	nf_ct_netns_put(ctx->net, ctx->family);
+}
+
 static const struct nft_chain_type nft_chain_nat_ipv6 = {
 	.name		= "nat",
 	.type		= NFT_CHAIN_T_NAT,

@@ -80,6 +90,8 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = {
 		[NF_INET_LOCAL_OUT]	= nft_nat_ipv6_local_fn,
 		[NF_INET_LOCAL_IN]	= nft_nat_ipv6_fn,
 	},
+	.init		= nft_nat_ipv6_init,
+	.free		= nft_nat_ipv6_free,
 };
 
 static int __init nft_chain_nat_ipv6_init(void)

index 97ec1c388bfe..af8b6a7488bd 100644
@@ -1211,13 +1211,17 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain,
 		rcu_assign_pointer(chain->stats, newstats);
 }
 
-static void nf_tables_chain_destroy(struct nft_chain *chain)
+static void nf_tables_chain_destroy(struct nft_ctx *ctx)
 {
+	struct nft_chain *chain = ctx->chain;
+
 	BUG_ON(chain->use > 0);
 
 	if (nft_is_base_chain(chain)) {
 		struct nft_base_chain *basechain = nft_base_chain(chain);
 
+		if (basechain->type->free)
+			basechain->type->free(ctx);
 		module_put(basechain->type->owner);
 		free_percpu(basechain->stats);
 		if (basechain->stats)

@@ -1354,6 +1358,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		}
 
 		basechain->type = hook.type;
+		if (basechain->type->init)
+			basechain->type->init(ctx);
+
 		chain = &basechain->chain;
 
 		ops		= &basechain->ops;

@@ -1374,6 +1381,8 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		if (chain == NULL)
 			return -ENOMEM;
 	}
+	ctx->chain = chain;
+
 	INIT_LIST_HEAD(&chain->rules);
 	chain->handle = nf_tables_alloc_handle(table);
 	chain->table = table;

@@ -1387,7 +1396,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	if (err < 0)
 		goto err1;
 
-	ctx->chain = chain;
 	err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (err < 0)
 		goto err2;

@@ -1399,7 +1407,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 err2:
 	nf_tables_unregister_hook(net, table, chain);
 err1:
-	nf_tables_chain_destroy(chain);
+	nf_tables_chain_destroy(ctx);
 
 	return err;
 }

@@ -5678,7 +5686,7 @@ static void nf_tables_commit_release(struct nft_trans *trans)
 		nf_tables_table_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_DELCHAIN:
-		nf_tables_chain_destroy(trans->ctx.chain);
+		nf_tables_chain_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_DELRULE:
 		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));

@@ -5849,7 +5857,7 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 		nf_tables_table_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_NEWCHAIN:
-		nf_tables_chain_destroy(trans->ctx.chain);
+		nf_tables_chain_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_NEWRULE:
 		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));

@@ -6499,7 +6507,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 	}
 	list_del(&ctx->chain->list);
 	ctx->table->use--;
-	nf_tables_chain_destroy(ctx->chain);
+	nf_tables_chain_destroy(ctx);
 
 	return 0;
 }

@@ -6515,6 +6523,7 @@ static void __nft_release_tables(struct net *net)
 	struct nft_set *set, *ns;
 	struct nft_ctx ctx = {
 		.net	= net,
+		.family	= NFPROTO_NETDEV,
 	};
 
 	list_for_each_entry_safe(table, nt, &net->nft.tables, list) {

@@ -6551,9 +6560,10 @@ static void __nft_release_tables(struct net *net)
 			nft_obj_destroy(obj);
 		}
 		list_for_each_entry_safe(chain, nc, &table->chains, list) {
+			ctx.chain = chain;
 			list_del(&chain->list);
 			table->use--;
-			nf_tables_chain_destroy(chain);
+			nf_tables_chain_destroy(&ctx);
 		}
 		list_del(&table->list);
 		nf_tables_table_destroy(&ctx);

index e26b94a61a99..bd2a18d66189 100644
@@ -434,11 +434,11 @@ static inline struct nft_set *nft_set_container_of(const void *priv)
 	return (void *)priv - offsetof(struct nft_set, data);
 }
 
-struct nft_set *nft_set_lookup(const struct net *net,
-			       const struct nft_table *table,
-			       const struct nlattr *nla_set_name,
-			       const struct nlattr *nla_set_id,
-			       u8 genmask);
+struct nft_set *nft_set_lookup_global(const struct net *net,
+				      const struct nft_table *table,
+				      const struct nlattr *nla_set_name,
+				      const struct nlattr *nla_set_id,
+				      u8 genmask);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {

index af8b6a7488bd..769d84015073 100644
@@ -2633,11 +2633,11 @@ static struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 	return ERR_PTR(-ENOENT);
 }
 
-struct nft_set *nft_set_lookup(const struct net *net,
-			       const struct nft_table *table,
-			       const struct nlattr *nla_set_name,
-			       const struct nlattr *nla_set_id,
-			       u8 genmask)
+struct nft_set *nft_set_lookup_global(const struct net *net,
+				      const struct nft_table *table,
+				      const struct nlattr *nla_set_name,
+				      const struct nlattr *nla_set_id,
+				      u8 genmask)
 {
 	struct nft_set *set;
 

@@ -2650,7 +2650,7 @@ struct nft_set *nft_set_lookup(const struct net *net,
 	}
 	return set;
 }
-EXPORT_SYMBOL_GPL(nft_set_lookup);
+EXPORT_SYMBOL_GPL(nft_set_lookup_global);
 
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)

index fc83e29d6634..04863fad05dd 100644
@@ -132,8 +132,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			priv->invert = true;
 	}
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_DYNSET_SET_NAME],
-			     tb[NFTA_DYNSET_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table,
+				    tb[NFTA_DYNSET_SET_NAME],
+				    tb[NFTA_DYNSET_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 

index 475570e89ede..f52da5e2199f 100644
@@ -71,8 +71,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	    tb[NFTA_LOOKUP_SREG] == NULL)
 		return -EINVAL;
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
-			     tb[NFTA_LOOKUP_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table, tb[NFTA_LOOKUP_SET],
+				    tb[NFTA_LOOKUP_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 

index 7bcdc48f3d73..0b02407773ad 100644
@@ -117,8 +117,9 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
 	struct nft_set *set;
 	int err;
 
-	set = nft_set_lookup(ctx->net, ctx->table, tb[NFTA_OBJREF_SET_NAME],
-			     tb[NFTA_OBJREF_SET_ID], genmask);
+	set = nft_set_lookup_global(ctx->net, ctx->table,
+				    tb[NFTA_OBJREF_SET_NAME],
+				    tb[NFTA_OBJREF_SET_ID], genmask);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 

index 769d84015073..2bd80fa9b070 100644
@@ -4032,17 +4032,10 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
 	if (err < 0)
 		return err;
 
-	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
-				   genmask);
-	if (IS_ERR(set)) {
-		if (nla[NFTA_SET_ELEM_LIST_SET_ID]) {
-			set = nf_tables_set_lookup_byid(net,
-					nla[NFTA_SET_ELEM_LIST_SET_ID],
-					genmask);
-		}
-		if (IS_ERR(set))
-			return PTR_ERR(set);
-	}
+	set = nft_set_lookup_global(net, ctx.table, nla[NFTA_SET_ELEM_LIST_SET],
+				    nla[NFTA_SET_ELEM_LIST_SET_ID], genmask);
+	if (IS_ERR(set))
+		return PTR_ERR(set);
 
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
 		return -EBUSY;

index 11ef85a57244..b00e84bf4107 100644
@@ -1527,9 +1527,8 @@ ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 	if (ret < 0)
 		return ret;
 
-	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
-					cda[CTA_NAT_SRC]);
-	return ret;
+	return ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC,
+					 cda[CTA_NAT_SRC]);
 #else
 	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
 		return 0;

index db2fe0911740..64fc3721d74c 100644
@@ -534,8 +534,7 @@ static u64 user2rate_bytes(u32 user)
 	u64 r;
 
 	r = user ? U32_MAX / user : U32_MAX;
-	r = (r - 1) << XT_HASHLIMIT_BYTE_SHIFT;
-	return r;
+	return (r - 1) << XT_HASHLIMIT_BYTE_SHIFT;
 }
 
 static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now,

index bac932f1c582..75cd5196b29b 100644
@@ -1854,7 +1854,9 @@ EXPORT_SYMBOL_GPL(xt_proto_fini);
  * to fetch the real percpu counter.
  *
  * To speed up allocation and improve data locality, a 4kb block is
- * allocated.
+ * allocated.  Freeing any counter may free an entire block, so all
+ * counters allocated using the same state must be freed at the same
+ * time.
  *
  * xt_percpu_counter_alloc_state contains the base address of the
  * allocated page and the current sub-offset.

index f366ff1cfc19..aaafdbd15ad3 100644
@@ -309,13 +309,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 	for (hook = 0; hook < NF_ARP_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
 		struct arpt_entry *e = entry0 + pos;
-		unsigned int last_pos, depth;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
 
-		depth = 0;
-		last_pos = pos;
 		/* Set initial back pointer. */
 		e->counters.pcnt = pos;
 

@@ -346,8 +343,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					pos = e->counters.pcnt;
 					e->counters.pcnt = 0;
 
-					if (depth)
-						--depth;
 					/* We're at the start. */
 					if (pos == oldpos)
 						goto next;

@@ -372,9 +367,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-
-					if (entry0 + newpos != arpt_next_entry(e))
-						++depth;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;

@@ -385,15 +377,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
-			if (depth == 0)
-				last_pos = pos;
-		}
-next:
-		if (last_pos != newinfo->underflow[hook]) {
-			pr_err_ratelimited("last base chain position %u doesn't match underflow %u (hook %u)\n",
-					   last_pos, newinfo->underflow[hook], hook);
-			return 0;
 		}
+next:		;
 	}
 	return 1;
 }

index 2362ca2c9e0c..f9063513f9d1 100644
@@ -378,13 +378,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
 		struct ipt_entry *e = entry0 + pos;
-		unsigned int last_pos, depth;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
 
-		depth = 0;
-		last_pos = pos;
 		/* Set initial back pointer. */
 		e->counters.pcnt = pos;
 

@@ -413,8 +410,6 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					pos = e->counters.pcnt;
 					e->counters.pcnt = 0;
 
-					if (depth)
-						--depth;
 					/* We're at the start. */
 					if (pos == oldpos)
 						goto next;

@@ -439,9 +434,6 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-
-					if (entry0 + newpos != ipt_next_entry(e))
-						++depth;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;

@@ -452,15 +444,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
-			if (depth == 0)
-				last_pos = pos;
-		}
-next:
-		if (last_pos != newinfo->underflow[hook]) {
-			pr_err_ratelimited("last base chain position %u doesn't match underflow %u (hook %u)\n",
-					   last_pos, newinfo->underflow[hook], hook);
-			return 0;
 		}
+next:		;
 	}
 	return 1;
 }

index 004508753abc..3c36a4c77f29 100644
@@ -396,13 +396,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
 	for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) {
 		unsigned int pos = newinfo->hook_entry[hook];
 		struct ip6t_entry *e = entry0 + pos;
-		unsigned int last_pos, depth;
 
 		if (!(valid_hooks & (1 << hook)))
 			continue;
 
-		depth = 0;
-		last_pos = pos;
 		/* Set initial back pointer. */
 		e->counters.pcnt = pos;
 

@@ -431,8 +428,6 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					pos = e->counters.pcnt;
 					e->counters.pcnt = 0;
 
-					if (depth)
-						--depth;
 					/* We're at the start. */
 					if (pos == oldpos)
 						goto next;

@@ -457,9 +452,6 @@ mark_source_chains(const struct xt_table_info *newinfo,
 					if (!xt_find_jump_offset(offsets, newpos,
 								 newinfo->number))
 						return 0;
-
-					if (entry0 + newpos != ip6t_next_entry(e))
-						++depth;
 				} else {
 					/* ... this is a fallthru */
 					newpos = pos + e->next_offset;

@@ -470,15 +462,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
 				e->counters.pcnt = pos;
 				pos = newpos;
 			}
-			if (depth == 0)
-				last_pos = pos;
-		}
-next:
-		if (last_pos != newinfo->underflow[hook]) {
-			pr_err_ratelimited("last base chain position %u doesn't match underflow %u (hook %u)\n",
-					   last_pos, newinfo->underflow[hook], hook);
-			return 0;
 		}
+next:		;
 	}
 	return 1;
 }

index 8f004edad396..f9d5a2a1e3d0 100644
@@ -72,9 +72,6 @@ hash_mac4_data_next(struct hash_mac4_elem *next,
 #define IP_SET_PROTO_UNDEF
 #include "ip_set_hash_gen.h"
 
-/* Zero valued element is not supported */
-static const unsigned char invalid_ether[ETH_ALEN] = { 0 };
-
 static int
 hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	       const struct xt_action_param *par,

@@ -93,7 +90,7 @@ hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		return -EINVAL;
 
 	ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
-	if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0)
+	if (is_zero_ether_addr(e.ether))
 		return -EINVAL;
 	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
 }

@@ -118,7 +115,7 @@ hash_mac4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (ret)
 		return ret;
 	ether_addr_copy(e.ether, nla_data(tb[IPSET_ATTR_ETHER]));
-	if (memcmp(e.ether, invalid_ether, ETH_ALEN) == 0)
+	if (is_zero_ether_addr(e.ether))
 		return -IPSET_ERR_HASH_ELEM;
 
 	return adtfn(set, &e, &ext, &ext, flags);